Watermarking is widely used to protect the ownership of tabular datasets. Comparing to non-blind watermarking that requires the original dataset to detect watermark, blind watermarking is more secure because it can accurately detect watermark without using the original dataset, which restricts public access to the original dataset. Existing blind watermarking methods rely on either a primary key or a virtual primary key to watermark a tabular dataset. However, these watermarks can be easily removed by an attacker with little to no impact on the dataset's machine learning utility, because a primary key can be significantly modified without affecting the machine learning utility, and a virtual primary key is fragile to slight modifications on the dataset. Can we design a blind watermarking method without relying on a primary key or virtual primary key? In this paper, we tackle this challenging task by a novel primary key free method that embeds a sinusoidal signal as the watermark into a discrete-time signal constructed from the tabular dataset. We theoretically analyzed the robustness of our watermark against six challenging attacks, and empirically validated the outstanding performance of our method through comprehensive experiments on two real-world datasets.

Generalized federated learning seeks to develop robust models across distributed source domains that generalize well to the unseen target domain. Mainstream methods make strict assumptions about the availability of target domain data, limiting the flexibility and adaptability of real-world applications. In this work, we tackle a real-world challenge that has never been addressed before: federated multi-source domain adaptation for an unseen target domain. We propose federated cross-domain semantic alignment with adversarial feature augmentation, a method that enhances model generalization across domains. Our method operates in the feature space to capture both diversity and invariance between source and target domains through a two-stage local training strategy. In the adversarial training phase, a domain identifier and feature discriminator constrain the generated features to extract target-relevant information. During the contrastive learning stage, a semantic representation alignment loss (SRA) is incorporated to align class prototype distributions between source and target domains, ensuring uniform classification standards. Federated aggregation consolidates model knowledge across clients, facilitating collaborative evolution and rapid adaptation to the unseen target domain. Extensive experimental results on four prevalent datasets demonstrate that our approach outperforms existing benchmarks across different backbones, showcasing its effectiveness in scenarios with data silos.

The task of dynamic graph link prediction is to forecast the evolution of complex systems. Empirical observations reveal that interactions within these systems exhibit an Entangled Spatio-Temporal Pattern, which manifests through three interrelated phenomena, namely Latent High-Order Bridges, Multi-Frequency Temporal Dynamics, and Spatio-Temporal Entanglement, with stronger structural ties facilitating tolerance for longer temporal gaps. However, limited by computationally prohibitive multi-hop sampling or inefficient long-sequence modeling, existing methods struggle to capture this complex pattern. Inspired by State-Space Models (SSMs) like Mamba for efficient long-range modeling yet aiming to address their native agnosticism to structural and multi-frequency dynamics, we propose a framework named DyGHydra, which couples a tailored Continuous-Time Hierarchical Mamba (CT-HMamba) backbone with a multi-hop structural encoder. The framework first employs the multi-hop structural encoder to reveal latent high-order interactions, extracting interaction-level cross-hop features. Subsequently, the CT-HMamba backbone utilizes these features to address multi-frequency dynamics through a hierarchical architecture, decomposing interaction history to simultaneously model high-frequency bursts and long-term trends. To capture the spatio-temporal entanglement, CT-HMamba further tailors its core state-space mechanism to be co-driven by physical time and structural context. Specifically, physical time governs the state transition decay to reflect temporal forgetting, while structural context modulates the input-output projections to prioritize topologically significant events. Extensive experiments on eleven real-world datasets show that DyGHydra achieves state-of-the-art performance across most settings for both transductive and inductive link prediction, validating its effectiveness in modeling complex temporal dynamics with superior efficiency.

Knowledge Distillation (KD) is a widely popular model compression technique that can effectively transfer knowledge from a pre-trained, large-scale teacher model to a more compact and lightweight student model. Traditional KD methods aim to improve the student’s representation capability by mimicking the teacher’s features, e.g., minimizing the \(\mathcal{L}_{2}\) distance between their intermediate features. However, due to the capacity gap between the student and the teacher, student often struggles to precisely mimic the features of the teacher. To address this challenge, we propose to boost the knowledge distillation for the visual recognition tasks via Direction Alignment and Discrepancy Standardization ( DADS) , which exploits the feature scaling technique to distill from both the feature direction and feature discrepancy. To this end, we devise an efficient feature alignment module to align the dimensions of teacher and student features. Moreover, we align the direction of student features and teacher features, which are pre-processed by normalization. Furthermore, we leverage the Kullback–Leibler (KL) divergence to refine the features alignment, minimizing discrepancy in the distribution of features across samples, which is pre-processed by \(\mathcal{Z}\) -score standardization. In this way, our proposed approach can effectively transfer the knowledge from the teacher to the student, facilitating the downstream visual recognition applications, such as image classification and semantic segmentation. Extensive experimental analyses clearly validate the effectiveness of DADS . Compared with previous KD methods, our approach sets a new benchmark, achieving state-of-the-art results on visual recognition tasks.

In recent years, axial data, where observations are treated as axes of direction, has gained prominence in a range of complex tasks, including gene expression data clustering, blind speech separation, and depth image analysis. However, prevailing methods for axial data modeling mainly rely on shallow probabilistic models, which often overlook the hidden and hierarchical dependencies in the latent space. These methods also require a separate, human-engineered feature extractor to obtain features from raw axial data for downstream tasks. This work introduces a novel framework, Axial Variational Autoencoders (AVAEs), for modeling and representation learning of axial data by leveraging a deep generative model, the Variational Autoencoder (VAE). Unlike existing approaches, our method can autonomously learn more expressive representations from axial data by designing a VAE that uses the Watson distribution as the latent prior. Furthermore, we introduce a tailored reparameterization technique to support stable training. We validate the effectiveness of our model through experiments on simulated axial datasets and a real-world application.

Graph Neural Networks (GNNs) have been widely used for learning representations of graph-structured data, achieving remarkable success in various graph-related Web applications, such as fraud detection. To generate node representations, GNN-based models operate message-passing mechanisms that aim to smooth the learned representations in a local neighborhood. However, fraudsters increasingly employ sophisticated “camouflage” tactics, exhibiting normal behaviors by strategically forming numerous connections with legitimate entities. As a result, existing GNN-based methods struggle to effectively tackle such fraudulent activities due to their reliance on homophily-based message-passing architectures. These methods fail to generate discriminative representations, which is crucial for distinguishing fraudsters from benign entities. To address this problem, we propose a novel Discriminative Enhanced Aggregation Graph Neural Network-based FraudDEtectioNMoDel (DEFEND) . DEFEND incorporates tailored discriminative mechanisms that strengthen representation learning at two complementary levels: (i) intra-relation and (ii) inter-relation. While prior approaches primarily focus on intra-relation patterns and overlook inter-relation information, DEFEND integrates both to capture subtle inconsistencies in fraudster behavior. Specifically, an edge discriminating mechanism classifies neighborhoods into homophily or heterophily-based views by leveraging node attributes and structural characteristics, and a camouflage-aware dual-channel aggregation module captures different frequencies of information tailored to these views to generate rich intra-relation node representations. While prior approaches typically rely on intra-relation information within each relation type, they overlook the discriminative signals that arise from correlations across different relations. In DEFEND, we observe that fraudsters often avoid forming consistent cross-relation interactions, whereas benign entities tend to establish them more frequently. This discrepancy creates a distinctive behavioral pattern. To capture this, we introduce an inter-relation correlation mechanism that correlates a node’s intra-relation representations across multiple relation types using an attention-based weighting scheme. By adaptively weighing the importance of each relation and integrating their contributions, DEFEND enhances the discriminative power of node representations. This mechanism enables the model to leverage both intra-relation and inter-relation levels of information, leading to richer and more robust representations for fraud detection. Finally, a multi-relation combination module aggregates information across different relation types, emphasizing the importance of node–relation pairs in the embedding. We conducted extensive experiments on two real-world fraud datasets to demonstrate the effectiveness of our proposed model, and our results show that DEFEND outperforms the state-of-the-art baselines. The source codes and datasets of our work are available at https://github.com/VenusHaghighi/DEFEND .

Corporate profiling serves as a critical analytical tool for modern enterprises, enabling data-driven decision-making in investment strategies, risk assessment, and strategic planning. It requires integrating quantitative metrics, qualitative insights, and network relationships to capture a company’s role in the business ecosystem. However, traditional methods struggle to synthesize heterogeneous data and model complex interdependencies among corporations, news, and market dynamics, often addressing these aspects in isolation. To address these challenges, this article introduces Financial Graph-based Mixture of Experts Prompt Learning (FGMPL), an innovative framework that unifies graph prompt learning with a multi-task paradigm for corporate profile modeling. The proposed framework reformulates node- and edge-level tasks into a coherent graph-level representation and employs multi-view contrastive learning to effectively integrate textual details with relational structures. Moreover, a novel Financial Multi-Experts Prompting mechanism—with learnable tokens coupled with a Mixture of Experts (MoE) design—is presented to enhance the processing of heterogeneous graph data and bridge the gap between pre-training and downstream tasks. To further improve adaptability, a meta-learning-based prompt tuning strategy is incorporated, enabling rapid transition to various downstream applications. Extensive experiments on real-world financial graphs show that FGMPL consistently outperforms strong pre-training and graph-prompting baselines across corporate performance prediction, relationship prediction, and news classification in both full-data and few-shot settings. In addition, cross-market transfer on a NASDAQ dataset and interpretability/efficiency analyses further demonstrate its robustness and practical applicability.

The next point-of-interest (POI) recommendation is a hot-spot for both industry and academia, which helps users better experience the physical world. However, existing methods suffer from a severe bias towards recommending repeat POIs that have been visited by the target user before, and perform inefficiently when recommending new POIs that have not been visited by the target user yet. To overcome this issue, we delve into the next new POI recommendation and uncover the coexistence of local and global exploration patterns in users’ visits to new POIs, showing their willingness to explore not only nearby new POIs but also those distant ones. Subsequently, we develop a novel L ocal and G lobal E xploration framework (LGE) for the next new POI recommendation. In particular, LGE involves three key modules: 1) a Zone-Aware Local Exploration (ZLE) module, which encourages users to explore POIs in the local area by learning zone-aware POI representations and regularizing POI prediction with zone information; 2) an Intention-Aware Global Exploration (IGE) module, which recommends POIs that meet user intentions without distance constraints by extracting static and dynamic intentions from category information; 3) a fusion module, which contains a Mean Pooling (MP) strategy and a Weighted Pooling (WP) strategy to aggregate the outputs of local and global exploration modules for the final recommendation. Experiments carried out on real-world datasets have shown the effectiveness of LGE in recommending new POIs.

Accurate estimation of the Individual Treatment Effect (ITE) is essential for business diagnostics in the online food delivery industry, particularly for assessing the impact of various business strategies, such as inventory management, pricing optimization and online marketing campaigns. A primary challenge in ITE estimation lies in sample selection bias. Conventional approaches utilize treatment regularization techniques such as Integral Probability Metrics (IPM), re-weighting, and propensity score modeling to mitigate this bias. However, these regularizations may introduce undesirable information loss and limit predictive performance. Moreover, treatment effects exhibit substantial heterogeneity across external contextual factors, such as market demand, competitor activity and time dynamics, yet existing methods fail to adequately model the interaction between treatments and context, limiting their causal expressiveness. To address these issues, we propose TSCAN: a Context-Aware uplift model based on a Two-Stage training approach, comprising CAN-U and CAN-D sub-models. In Stage 1, CAN-U generates counterfactual uplift labels while mitigating selection bias through integrated IPM and propensity score regularization. In Stage 2, CAN-D eliminates these regularizations and leverages an isotonic output layer to directly model uplift effects in a supervised manner. By reinforcing factual outcomes, CAN-D adaptively corrects estimation errors from CAN-U while circumventing the performance degradation induced by bias-mitigation regularizations. Additionally, both stages incorporate a Context-Aware Attention mechanism that dynamically fuses the embeddings of merchants, treatments and contextual covariates, thereby capturing context-dependent heterogeneity in treatment effects. We conduct extensive experiments on two real-world datasets to validate the effectiveness of TSCAN. Ultimately, the deployment of our model for real-world merchant diagnosis on one of China’s largest online food ordering platforms validates its practical utility and impact.

Self-supervised heterogeneous graph representation learning (SSHGRL) is a key technique for embedding heterogeneous graphs, enabling effective analysis and modeling of social networks and other graph-structured data, which are central to knowledge discovery and the study of social systems. However, existing SSHGRL methods are hardly applied to large-scale heterogeneous graph environments due to the normally-used metapath decomposing mechanism being graph-size-sensitive. Moreover, the existing self-supervised signals are normally created from Shared Mutual Information (SMI) of different graph views that ignore the Non-shared Mutual Information (NMI) contained in the same view. This results in the model tending to learn insufficient graph representation. To this end, this paper proposes a designated masking propagation (DMP) mechanism to process heterogeneous graphs without using metapath. Moreover, based on the DMP graph view, a novel sufficient representation is proposed to learn the effective graph representation by combining both NMI and SMI. Extensive experiments on eight large- and medium-scale heterogeneous graph datasets demonstrate the superiority of our method, setting new state-of-the-art performance in various big data contexts.